Robotics: Science and Systems XIV

Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties

Juekun Li, Wee Sun Lee, David Hsu

Abstract:

This paper introduces Push-Net, a deep recurrent neural network model, which enables a robot to push ob- jects of unknown physical properties for re-positioning and re-orientation, using only visual camera images as input. The unknown physical properties is a major challenge for pushing. Push-Net overcomes the challenge by tracking a history of push interactions with an LSTM module and training an auxiliary objective function that estimates an object’s center of mass. We trained Push-Net entirely in simulation and tested it extensively on many different objects in both simulation and on two real robots, a Fetch arm and a Kinova MICO arm. Experiments suggest that Push-Net is robust and efficient. It achieved over 97% success rate in simulation on average and succeeded in all real robot experiments with a small number of pushes.

Download:

Bibtex:

  
@INPROCEEDINGS{Li-RSS-18, 
    AUTHOR    = {Juekun Li AND Wee Sun Lee AND David Hsu}, 
    TITLE     = {Push-Net: Deep Planar Pushing for Objects with Unknown Physical Properties}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2018}, 
    ADDRESS   = {Pittsburgh, Pennsylvania}, 
    MONTH     = {June}, 
    DOI       = {10.15607/RSS.2018.XIV.024} 
}